A New Method for Stealthy False Data Injection Attack Detection Using Advanced Feasibility Areas Considering Spatial Distribution
Bibliographic record
Abstract
The Feasibility Area (FA) in power system applications defines the region within which Power System State Variables (PSSVs) typically exist under normal operating conditions. Accurate characterization of the FA helps enhancing optimal power flow, detecting anomalies, and identifying stealthy False Data Injection Attacks (FDIAs). Traditional FA-based approaches assess the location of PSSVs based on discrete time instances, using a binary flag to indicate whether the PSSVs lie inside or outside the FA. This paper introduces an advanced FA-based stealthy FDIAs detection method that improves upon this by incorporating the spatial distribution of PSSVs relative to the estimated FA. Unlike conventional methods, the advanced FA incorporates spatial distribution to evaluate the proximity of the current PSSV to the expected FA in the complex plane. A sigmoid-expansion flag is employed to represent the probability of the current PSSVs belonging to the expected FA, replacing the conventional binary flag. This sigmoid-expansion flag is then used as an input to a Deep Neural Network (DNN), where both the sigmoid-expansion flag and DNN model parameters are fine-tuned during training to ensure optimal compatibility, thereby improving detection accuracy. The proposed method significantly improves the detection of stealthy FDIAs, offering superior performance over traditional FA. Additionally, it enables the extraction of key attack characteristics, such as type, nature, and magnitude, further strengthening the system’s defense capabilities.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".